Skip to main content

Academic Papers

Key research papers in AI and language models with direct links to sources.

Foundation Models

LLaMA: Open and Efficient Foundation Language Models (2023)
arXiv | Meta AI
LLaMA-13B outperforms GPT-3 (175B) using only public data

LLaMA 2: Open Foundation and Fine-Tuned Chat Models (2023)
arXiv | Meta AI
First open-source models with commercial license and safety focus

Gemma: Open Models Based on Gemini Research (2024)
arXiv | Google
Efficient 2B and 7B models ideal for edge computing

Architecture

Attention Is All You Need (2017)
arXiv | Google
Introduced Transformer architecture, foundation of all modern LLMs

Safety & Alignment

A Survey on Hallucination in Large Language Models (2023)
arXiv
Systematic analysis of LLM hallucination problems and solutions

Theory of Mind in Large Language Models (2023)
arXiv | Stanford
Evidence of emergent cognitive abilities in GPT models

Applications

ChatGPT and Software Testing Education (2023)
arXiv
Evaluation of LLMs in software testing tasks

Faith and Fate: Limits of Transformers on Compositionality (2023)
arXiv
Fundamental limitations in compositional reasoning

Philosophy

The Illusion of Thinking: Cognitive Science of LLMs (2023)
arXiv
Philosophical analysis of whether LLMs truly "think"

A Survey on Large Language Models (2023)
arXiv
Comprehensive review of LLM evolution from BERT to ChatGPT